© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9019
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic devices and technology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aziland
    -0.84
     Brookfield
    -0.84
     Swaziland
    -0.74
    Eloquent
    -0.72
     Guido
    -0.71
     himo
    -0.70
     estimés
    -0.70
    tament
    -0.70
    DeleteBehavior
    -0.69
     Cain
    -0.69
    POSITIVE LOGITS
     Electronic
    1.08
     electronic
    1.07
    electronic
    1.04
     ELECTRONIC
    1.03
    Electronic
    1.02
     electronics
    1.00
     elektronik
    0.91
     Electronics
    0.90
    electronics
    0.85
    elektron
    0.84
    Activations Density 0.008%

    No Known Activations